# Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations

arXiv: https://arxiv.org/abs/2503.09867 · HTML: https://mlsanity.com/paper/2503.09867/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 36 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Illiterate DALL-E Learns to Compose](https://mlsanity.com/paper/2110.11405/) (2021)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [R2Former: Unified Retrieval and Reranking Transformer for Place Recognition](https://mlsanity.com/paper/2304.03410/) (2023)
- [Deep Hierarchical Planning from Pixels](https://mlsanity.com/paper/2206.04114/) (2022)
- [ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/2111.10265/) (2021)
- [Large Language Models as Generalizable Policies for Embodied Tasks](https://mlsanity.com/paper/2310.17722/) (2023)
- [SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models](https://mlsanity.com/paper/2305.11281/) (2023)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Making Efficient Use of Demonstrations to Solve Hard Exploration Problems](https://mlsanity.com/paper/1909.01387/) (2019)
- [From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons](https://mlsanity.com/paper/2412.08442/) (2024)
- [A Survey of Embodied Learning for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2408.11537/) (2024)
- [Adaptive Slot Attention: Object Discovery with Dynamic Slot Number](https://mlsanity.com/paper/2406.09196/) (2024)
- [Slot-VAE: Object-Centric Scene Generation with Slot Attention](https://mlsanity.com/paper/2306.06997/) (2023)
- [A Perspective on Objects and Systematic Generalization in Model-Based RL](https://mlsanity.com/paper/1906.01035/) (2019)
- [Learning to Compose: Improving Object Centric Learning by Injecting Compositionality](https://mlsanity.com/paper/2405.00646/) (2024)

## Abstract (arXiv)

Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO have shown emergent object understanding. We investigate the effectiveness of self-supervised representations from models such as CLIP, DINOv2 and DINOv3, as well as slot-based approaches, for multi-object instance retrieval, where specific objects must be faithfully identified in a scene. This scenario is increasingly relevant as pre-trained representations are deployed in downstream tasks, e.g., retrieval, manipulation, and goal-conditioned policies that demand fine-grained object understanding. Our findings reveal that self-supervised vision models and slot-based representations excel at identifying edge-derived geometry (shape, size) but fail to preserve non-geometric surface-level cues (colour, material, texture), which are critical for disambiguating objects when reasoning about or selecting them in such tasks. We show that learning an auxiliary latent space over segmented patches, where VAE regularisation enforces compact, disentangled object-centric representations, recovers these missing attributes. Augmenting the self-supervised methods with such latents improves retrieval across all attributes, suggesting a promising direction for making self-supervised representations more reliable in downstream tasks that require precise object-level reasoning.